Skip to content
This repository has been archived by the owner on Jan 3, 2023. It is now read-only.

CPU optimizations bringing 7x gain in Deep Speech 2 performance and gains in Alexnet, VGG
Compare
Choose a tag to compare
@jennifermyers jennifermyers released this 27 Oct 15:18
· 54 commits to master since this release
v2.3.0
9eb09d7
  • Optimized DeepSpeech2 MKL backend performance (~7X improvement over the CPU backend)
  • Fused convolution and bias layer which significantly boosted AlexNet and VGG performance on Intel architectures with MKL backend
  • Made SSD and Faster-RNN use VGG weight files in new format
  • Fixed use of reset_cells hyperparameter
  • Fixed MKL backend bug for GAN and Faster-RCNN models
Assets 2
Loading